mirror of
https://github.com/explosion/spaCy.git
synced 2025-10-31 16:07:41 +03:00
e2b70df012
* Use isort with Black profile * isort all the things * Fix import cycles as a result of import sorting * Add DOCBIN_ALL_ATTRS type definition * Add isort to requirements * Remove isort from build dependencies check * Typo
70 lines
2.7 KiB
Python
70 lines
2.7 KiB
Python
from pathlib import Path
|
|
|
|
from wasabi import msg
|
|
|
|
from .._util import Arg, load_project_config, logger, project_cli
|
|
from .remote_storage import RemoteStorage, get_command_hash, get_content_hash
|
|
|
|
|
|
@project_cli.command("push")
|
|
def project_push_cli(
|
|
# fmt: off
|
|
remote: str = Arg("default", help="Name or path of remote storage"),
|
|
project_dir: Path = Arg(Path.cwd(), help="Location of project directory. Defaults to current working directory.", exists=True, file_okay=False),
|
|
# fmt: on
|
|
):
|
|
"""Persist outputs to a remote storage. You can alias remotes in your
|
|
project.yml by mapping them to storage paths. A storage can be anything that
|
|
the smart-open library can upload to, e.g. AWS, Google Cloud Storage, SSH,
|
|
local directories etc.
|
|
|
|
DOCS: https://spacy.io/api/cli#project-push
|
|
"""
|
|
for output_path, url in project_push(project_dir, remote):
|
|
if url is None:
|
|
msg.info(f"Skipping {output_path}")
|
|
else:
|
|
msg.good(f"Pushed {output_path} to {url}")
|
|
|
|
|
|
def project_push(project_dir: Path, remote: str):
|
|
"""Persist outputs to a remote storage. You can alias remotes in your project.yml
|
|
by mapping them to storage paths. A storage can be anything that the smart-open
|
|
library can upload to, e.g. gcs, aws, ssh, local directories etc
|
|
"""
|
|
config = load_project_config(project_dir)
|
|
if remote in config.get("remotes", {}):
|
|
remote = config["remotes"][remote]
|
|
storage = RemoteStorage(project_dir, remote)
|
|
for cmd in config.get("commands", []):
|
|
logger.debug("CMD: %s", cmd["name"])
|
|
deps = [project_dir / dep for dep in cmd.get("deps", [])]
|
|
if any(not dep.exists() for dep in deps):
|
|
logger.debug("Dependency missing. Skipping %s outputs", cmd["name"])
|
|
continue
|
|
cmd_hash = get_command_hash(
|
|
"", "", [project_dir / dep for dep in cmd.get("deps", [])], cmd["script"]
|
|
)
|
|
logger.debug("CMD_HASH: %s", cmd_hash)
|
|
for output_path in cmd.get("outputs", []):
|
|
output_loc = project_dir / output_path
|
|
if output_loc.exists() and _is_not_empty_dir(output_loc):
|
|
url = storage.push(
|
|
output_path,
|
|
command_hash=cmd_hash,
|
|
content_hash=get_content_hash(output_loc),
|
|
)
|
|
logger.debug(
|
|
"URL: %s for output %s with cmd_hash %s", url, output_path, cmd_hash
|
|
)
|
|
yield output_path, url
|
|
|
|
|
|
def _is_not_empty_dir(loc: Path):
|
|
if not loc.is_dir():
|
|
return True
|
|
elif any(_is_not_empty_dir(child) for child in loc.iterdir()):
|
|
return True
|
|
else:
|
|
return False
|